© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 217591
    Prev
    Next
    INDEX
    Explanations

    page numbers and certain foreign characters

    np_acts-logits-general · gemini-2.5-flash-lite

    non-english words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     b
    0.51
     lord
    0.46
     cmp
    0.45
     r
    0.45
    ida
    0.44
     both
    0.44
     swelling
    0.44
     B
    0.42
    _
    0.42
     S
    0.42
    POSITIVE LOGITS
    לה
    0.53
    лам
    0.50
    티
    0.49
    コロ
    0.48
    ्तार
    0.48
    לע
    0.48
    בד
    0.47
    柬
    0.47
    ቬ
    0.47
    脲
    0.47
    Activations Density 0.001%

    No Known Activations